Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3133 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3694. Min Range: -3.3694

Max Act: 3.2085. Min Act: -0.0000

Data Index: 1277063 (C4 (Web Text))

Max Activating Token Index: 990

Text #1

Max Range: 3.3694. Min Range: -3.3694

Max Act: 3.3694. Min Act: -0.0000

Data Index: 1329293 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.6925. Min Act: -0.0000

Data Index: 824127 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.4875. Min Act: -0.0000

Data Index: 1077483 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.7023. Min Act: -0.0000

Data Index: 1123602 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.4155. Min Act: -0.0000

Data Index: 1110342 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.5492. Min Act: -0.0000

Data Index: 643996 (C4 (Web Text))

Max Activating Token Index: 435

Text #7

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.4178. Min Act: -0.0000

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 242

Text #8

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.5048. Min Act: -0.0000

Data Index: 325060 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.6301. Min Act: -0.0000

Data Index: 422714 (C4 (Web Text))

Max Activating Token Index: 950

Text #10

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.4274. Min Act: -0.0000

Data Index: 92710 (C4 (Web Text))

Max Activating Token Index: 517

Text #11

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.3421. Min Act: -0.0000

Data Index: 75995 (C4 (Web Text))

Max Activating Token Index: 901

Text #12

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.4272. Min Act: -0.0000

Data Index: 101964 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.3583. Min Act: -0.0000

Data Index: 621567 (C4 (Web Text))

Max Activating Token Index: 325

Text #14

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.2542. Min Act: -0.0000

Data Index: 881002 (C4 (Web Text))

Max Activating Token Index: 593

Text #15

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.2354. Min Act: -0.0000

Data Index: 199674 (C4 (Web Text))

Max Activating Token Index: 858

Text #16

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.3398. Min Act: -0.0000

Data Index: 1193167 (C4 (Web Text))

Max Activating Token Index: 511

Text #17

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.1753. Min Act: -0.0000

Data Index: 434300 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.1576. Min Act: -0.0000

Data Index: 115436 (C4 (Web Text))

Max Activating Token Index: 774

Text #19

Max Range: 3.3694. Min Range: -3.3694

Max Act: 2.0902. Min Act: -0.0000

Data Index: 725691 (C4 (Web Text))

Max Activating Token Index: 138